Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds that no authentication is required and that data is CC BY 4.0 from macrostrat.org/api/v2, which is valuable behavioral context. It also enumerates the payload fields (ages, thickness, etc.), giving a concrete sense of what a call returns. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. The first sentence front-loads the tool's action, returned attributes, and lookup keys; the second provides source, auth, and licensing in a compact list. Each clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The combination of description, annotations, and the presence of an output schema gives an agent everything needed to select and invoke this tool. It covers purpose, lookup methods, parameter sources, auth requirements, licensing, and safety profile. The only minor unknown is whether col_id and lat/lng can be combined, but the description's 'or' implies exclusivity without hindering correct use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all three parameters with descriptions, so baseline is 3. The description adds meaning by specifying that col_id comes from macrostrat.columns_search, and by presenting col_id and lat/lng as alternative lookup modes. This goes beyond the schema's per-property descriptions, which only note that lat and lng must be provided together.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Get') and resource ('rock units ... that make up a stratigraphic column') and lists the fields returned (formation/member/group names, ages, thickness, lithology, depositional environment). It also names the two lookup methods (col_id or lat/lng) and the source API. It does not explicitly contrast with the sibling tool 'map_units', but the 'stratigraphic column' scoping distinguishes it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clearly explains how to invoke: either with a col_id (pointing to macrostrat.columns_search as its source) or with lat/lng coordinates. This is useful contextual guidance. But it does not explicitly state when not to use it or which alternative tools to prefer for other geology queries (e.g., fossils_search).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.